Learning in Public Voice
House style for learning-in-public essays — a curious practitioner thinking out loud while learning a hard technical subject (here, ML-driven crop genetics / genomic selection). First-person, concrete-first, honest about the edge of understanding, mechanism over vocabulary. Provides the register, the hook patterns, the anti-slop hard rules, and the rule for reading a per-writer voice-profile.md so the voice stays the writer's own. Use when drafting a vault-style post from evergreen notes, or as the lens an advisory editor critiques against. This skill never imposes voice; it describes defaults
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill learning-in-public-voicegit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/learning-in-public-voice ~/.claude/skills/learning-in-public-voicePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Learning-in-public voice This is the house style for essays that a data scientist writes *while learning* a technical subject in public — short pieces that turn a day's reading and a small experiment into one earned claim. The model is a practitioner thinking out loud, not an authority lecturing. The reference voices are people who write to understand: they start from a thing they observed, follow the confusion honestly, and land on one idea they can now defend. This skill is a **lens, not a cage.** The writer's actual idiolect lives in `writing/voice-profile.md` in their vault. That file always wins. This skill supplies sensible defaults and a vocabulary for talking about voice so an editor can flag a deviation as a *suggestion* without ever overwriting the writer's words. When this skill and the profile disagree, follow the profile and note the difference. ## The register - **First person, learning in motion.** "I kept reading heritability as a property of the trait until a simulation forced me to see it as a property of the population." The reader watches understanding form. - **Concrete first, concept second.** Open on the observed thing — a number, a plot, a failed prediction, a line of a VCF file — then reach for the idea that explains it. Never open by defining the topic.
Details
- Skill name
learning-in-public-voice- Repository
- lyndonkl/claude
- Path
skills/learning-in-public-voice/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Learning in Public Voice skill do?
House style for learning-in-public essays — a curious practitioner thinking out loud while learning a hard technical subject (here, ML-driven crop genetics / genomic selection). First-person, concrete-first, honest about the edge of understanding, mechanism over vocabulary. Provides the register, the hook patterns, the anti-slop hard rules, and the rule for reading a per-writer voice-profile.md so the voice stays the writer's own. Use when drafting a vault-style post from evergreen notes, or as the lens an advisory editor critiques against. This skill never imposes voice; it describes defaults
How do I install the Learning in Public Voice skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Learning in Public Voice popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
Academic Letter Architect
200lyndonkl/claude
Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
Adr Architecture
200lyndonkl/claude
Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
Platform Voice Check
200lyndonkl/claude
Runs a voice-fidelity audit on each of the four substacker platform outputs (Substack Note, X thread, LinkedIn post, cross-post blurb) before reporting Distribution Translator completion. Checks for voice-don'ts (banned vocabulary, emoji, generic openers, marketing math without source), voice-do compliance (paper attribution preserved, hedges preserved, em-dash reframes present), platform-specific tonal shifts. Emits voice-check.md with pass/fail per artifact. Trigger keywords — platform voice check, voice-check, gate, distribution voice, slop-leak check.
High Dim Intuition Rebuild
200lyndonkl/claude
Diagnoses where a learner's 3D geometric intuition is misleading them in a high-dimensional context (concentration of measure, Gaussian shells, distance-metric breakdown, manifold hypothesis, volume-in-corners, random-projection preservation), then surgically replaces the false picture with the correct one. Use when the user is reasoning about high-dim spaces (embeddings, latent vectors, neural net activations, large-scale data clouds, optimization landscapes) and either makes a claim that's true in 3D but false in 1000D, or expresses confusion at a high-dim phenomenon that "shouldn't" happen.
Prose Force and Rhythm
200lyndonkl/claude
Runs Jack Hart's Wordcraft line passes in strict order (Structure, Force, Brevity, Clarity, Rhythm, Humanity, Color, Voice, Mechanics) followed by a slop audit, one pass per edit class, with a claim-strength invariant that stops verb strengthening and hedge cutting from silently overclaiming. Enforces upward escalation instead of downward compensation, a protected-hedge list, a clarity split log the rhythm pass may not undo, and rhythm metrics reported as diagnostics rather than optimized. Use when line-editing a draft, tightening flabby prose, fixing weak verbs or monotonous sentence rhythm,
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.